Computer storage medium, computer program product, method for monitoring fault of wind power generator set, and device

Abstract

A method and device for monitoring a fault of a wind power generator set. The method includes the following steps: performing (101) fault identification on a component in a wind power generator set; and presenting (102) an identified fault using a three-dimensional model of the component. The device includes corresponding identifying module (61) and presenting module (62). By using the method and device, the fault monitor can intuitively observe the fault existed in the component, which not only is beneficial for taking effective fault processing measures before a minor fault evolves into a serious fault and thus reduces the harm of the fault, but also reduces the experience requirements for the fault monitor and avoids the process that the fault monitor in the prior art analyzes a two-dimensional curve to identify whether there is a fault in the component according to his experience.

What is claimed is: 
     
       1. A method for monitoring a fault of a wind power generator set, comprising:
 performing fault identification on a component in the wind power generator set; and 
 presenting an identified fault using a three-dimensional model of the component; 
 wherein the presenting the identified fault using the three-dimensional model of the component comprises: 
 inputting a set of sensor data of the component collected by a sensor into state functions corresponding to respective state modes to obtain respective judgment values; and 
 determining a most matching state mode from the respective state modes according to the judgment values of the respective state functions; 
 if the most matching state mode is a normal state mode, determining that there is no fault in the component, otherwise, determining the most matching state mode as a fault mode of the component; 
 judging a target fault mode of the component according to value ranges of physical parameters of the component in a characteristic testing matrix under each fault mode; 
 identifying a target three-dimensional model corresponding to the target fault mode and the value ranges of the physical parameters from a pool of the three-dimensional model of the component; and 
 presenting the target three-dimensional model. 
 
     
     
       2. The method for monitoring the fault of the wind power generator set according to  claim 1 , wherein the performing the fault identification on the component in the wind power generator set comprises:
 collecting a set of sensor data of the component using a sensor; 
 performing data analysis on the set of sensor data using a pre-trained machine learning model to obtain a characteristic testing matrix; a row vector of the characteristic testing matrix is used to indicate the component, and a column vector thereof is used to indicate a physical parameter; and 
 performing the fault identification according to the characteristic testing matrix. 
 
     
     
       3. The method for monitoring the fault of the wind power generator set according to  claim 2 , wherein the presenting the identified fault using the three-dimensional model of the component comprises:
 extracting, for the identified component with the fault, a mechanical parameter from the physical parameter of the component with the fault; 
 determining a value of the mechanical parameter of the component with the fault according to the characteristic testing matrix; and 
 taking the value of the mechanical parameter as a boundary condition, and performing stress analysis on a normal-state three-dimensional model of the component with the fault to obtain a three-dimensional model presenting a stress state. 
 
     
     
       4. The method for monitoring the fault of the wind power generator set according to  claim 2 , wherein the performing the fault identification according to the characteristic testing matrix comprises:
 determining the component as operating normally if a value of the physical parameter of the component in the characteristic testing matrix matches with a value of the physical parameter in a design state; 
 otherwise, identifying that there is a fault in the component; and 
 querying, in a fault database, a target fault mode that matches with the value of the physical parameter of the component in the characteristic testing matrix. 
 
     
     
       5. The method for monitoring the fault of the wind power generator set according to  claim 2 , wherein the physical parameter comprises: rotation shaft torque T, inherent frequency H, frictional force Ff, reflective light intensity U, power W transmitted by a shaft, output power P, rotational speed N, pressure Fp, wind speed V, an impeller diameter D, mass M of the component and/or a pixel O;
 wherein the rotation shaft torque T, the frictional force Ff and the pressure Fp belong to the mechanical parameter. 
 
     
     
       6. The method for monitoring the fault of the wind power generator set according to  claim 1 , wherein after presenting the identified fault using the three-dimensional model of the component, the method further comprises:
 querying in a solution database to obtain a solution corresponding to the target fault mode of the component; and 
 processing the fault of the component according to the solution, and/or outputting the solution. 
 
     
     
       7. A computer non-transitory storage medium, wherein a computer program is stored on the non-transitory computer storage medium, and the computer program causes a computer to perform the method for monitoring the fault of the wind power generator set according to  claim 1 .